Machine learning calibration of low-cost NO2 and PM10 sensors: non-linear algorithms and their impact on site transferability
Low-cost air pollution sensors often fail to attain sufficient performance compared with state-of-the-art measurement stations, and they typically require expensive laboratory-based calibration procedures. A repeatedly proposed strategy to overcome these limitations is calibration through co-locatio...
Uloženo v:
| Vydáno v: | Atmospheric measurement techniques Ročník 14; číslo 8; s. 5637 - 5655 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Katlenburg-Lindau
Copernicus GmbH
18.08.2021
Copernicus Publications |
| Témata: | |
| ISSN: | 1867-1381, 1867-8548 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Low-cost air pollution sensors often fail to attain sufficient performance compared with state-of-the-art measurement stations, and they typically require expensive laboratory-based calibration procedures. A repeatedly proposed strategy to overcome these limitations is calibration through co-location with public measurement stations. Here we test the idea of using machine learning algorithms for such calibration tasks using hourly-averaged co-location data for nitrogen dioxide (NO2) and particulate matter of particle sizes smaller than 10 µm (PM10) at three different locations in the urban area of London, UK. We compare the performance of ridge regression, a linear statistical learning algorithm, to two non-linear algorithms in the form of random forest regression (RFR) and Gaussian process regression (GPR). We further benchmark the performance of all three machine learning methods relative to the more common multiple linear regression (MLR). We obtain very good out-of-sample R2 scores (coefficient of determination) >0.7, frequently exceeding 0.8, for the machine learning calibrated low-cost sensors. In contrast, the performance of MLR is more dependent on random variations in the sensor hardware and co-located signals, and it is also more sensitive to the length of the co-location period. We find that, subject to certain conditions, GPR is typically the best-performing method in our calibration setting, followed by ridge regression and RFR. We also highlight several key limitations of the machine learning methods, which will be crucial to consider in any co-location calibration. In particular, all methods are fundamentally limited in how well they can reproduce pollution levels that lie outside those encountered at training stage. We find, however, that the linear ridge regression outperforms the non-linear methods in extrapolation settings. GPR can allow for a small degree of extrapolation, whereas RFR can only predict values within the training range. This algorithm-dependent ability to extrapolate is one of the key limiting factors when the calibrated sensors are deployed away from the co-location site itself. Consequently, we find that ridge regression is often performing as good as or even better than GPR after sensor relocation. Our results highlight the potential of co-location approaches paired with machine learning calibration techniques to reduce costs of air pollution measurements, subject to careful consideration of the co-location training conditions, the choice of calibration variables and the features of the calibration algorithm. |
|---|---|
| AbstractList | Low-cost air pollution sensors often fail to attain sufficient performance compared with state-of-the-art measurement stations, and they typically require expensive laboratory-based calibration procedures. A repeatedly proposed strategy to overcome these limitations is calibration through co-location with public measurement stations. Here we test the idea of using machine learning algorithms for such calibration tasks using hourly-averaged co-location data for nitrogen dioxide (NO 2 ) and particulate matter of particle sizes smaller than 10 µm (PM 10 ) at three different locations in the urban area of London, UK. We compare the performance of ridge regression, a linear statistical learning algorithm, to two non-linear algorithms in the form of random forest regression (RFR) and Gaussian process regression (GPR). We further benchmark the performance of all three machine learning methods relative to the more common multiple linear regression (MLR). We obtain very good out-of-sample R2 scores (coefficient of determination) >0.7 , frequently exceeding 0.8, for the machine learning calibrated low-cost sensors. In contrast, the performance of MLR is more dependent on random variations in the sensor hardware and co-located signals, and it is also more sensitive to the length of the co-location period. We find that, subject to certain conditions, GPR is typically the best-performing method in our calibration setting, followed by ridge regression and RFR. We also highlight several key limitations of the machine learning methods, which will be crucial to consider in any co-location calibration. In particular, all methods are fundamentally limited in how well they can reproduce pollution levels that lie outside those encountered at training stage. We find, however, that the linear ridge regression outperforms the non-linear methods in extrapolation settings. GPR can allow for a small degree of extrapolation, whereas RFR can only predict values within the training range. This algorithm-dependent ability to extrapolate is one of the key limiting factors when the calibrated sensors are deployed away from the co-location site itself. Consequently, we find that ridge regression is often performing as good as or even better than GPR after sensor relocation. Our results highlight the potential of co-location approaches paired with machine learning calibration techniques to reduce costs of air pollution measurements, subject to careful consideration of the co-location training conditions, the choice of calibration variables and the features of the calibration algorithm. Low-cost air pollution sensors often fail to attain sufficient performance compared with state-of-the-art measurement stations, and they typically require expensive laboratory-based calibration procedures. A repeatedly proposed strategy to overcome these limitations is calibration through co-location with public measurement stations. Here we test the idea of using machine learning algorithms for such calibration tasks using hourly-averaged co-location data for nitrogen dioxide (NO2) and particulate matter of particle sizes smaller than 10 µm (PM10) at three different locations in the urban area of London, UK. We compare the performance of ridge regression, a linear statistical learning algorithm, to two non-linear algorithms in the form of random forest regression (RFR) and Gaussian process regression (GPR). We further benchmark the performance of all three machine learning methods relative to the more common multiple linear regression (MLR). We obtain very good out-of-sample R2 scores (coefficient of determination) >0.7, frequently exceeding 0.8, for the machine learning calibrated low-cost sensors. In contrast, the performance of MLR is more dependent on random variations in the sensor hardware and co-located signals, and it is also more sensitive to the length of the co-location period. We find that, subject to certain conditions, GPR is typically the best-performing method in our calibration setting, followed by ridge regression and RFR. We also highlight several key limitations of the machine learning methods, which will be crucial to consider in any co-location calibration. In particular, all methods are fundamentally limited in how well they can reproduce pollution levels that lie outside those encountered at training stage. We find, however, that the linear ridge regression outperforms the non-linear methods in extrapolation settings. GPR can allow for a small degree of extrapolation, whereas RFR can only predict values within the training range. This algorithm-dependent ability to extrapolate is one of the key limiting factors when the calibrated sensors are deployed away from the co-location site itself. Consequently, we find that ridge regression is often performing as good as or even better than GPR after sensor relocation. Our results highlight the potential of co-location approaches paired with machine learning calibration techniques to reduce costs of air pollution measurements, subject to careful consideration of the co-location training conditions, the choice of calibration variables and the features of the calibration algorithm. |
| Author | Nowack, Peer Gardiner, Hannah Konstantinovskiy, Lev Cant, John |
| Author_xml | – sequence: 1 givenname: Peer surname: Nowack fullname: Nowack, Peer – sequence: 2 givenname: Lev surname: Konstantinovskiy fullname: Konstantinovskiy, Lev – sequence: 3 givenname: Hannah surname: Gardiner fullname: Gardiner, Hannah – sequence: 4 givenname: John surname: Cant fullname: Cant, John |
| BookMark | eNotjklLBDEQRoMoqKN3jwHP0WzdSbyJuAy4HfTc1GSZydCTjElE5uB_t1EvVcXHV493jPZTTh6hM0YvOmbkJWwaYZJ0vVCEU8720BHTvSK6k3r__2ZCs0N0XOua0l4yxY_Q9xPYVUwejx5KimmJLYxxUaDFnHAOeMxfxOba8PMLx5Acfn1iFFefai71Ck8WZJz-oWAYl7nEttrU315b-Vhw3GzBNjyxamwetwKpBl9gEcfYdifoIMBY_en_nqH3u9u3mwfy-HI_v7l-JI5L04gzQL0BI1hgQlKnpWHayc5LEZQKnppeB-WlksqohXXgheBuGiClAQFihuZ_XJdhPWxL3EDZDRni8BvkshygtGhHP_Rh4XqpbOgYk12ngGrunFVgOVjgamKd_7G2JX98-tqGdf4sadIfeNdzzqk2XPwAm4t8YA |
| ContentType | Journal Article |
| Copyright | 2021. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2021. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | 7QH 7TG 7TN 7UA 8FD 8FE 8FG ABUWG AEUYN AFKRA ARAPS AZQEC BENPR BFMQW BGLVJ BHPHI BKSAR C1K CCPQU DWQXO F1W H8D H96 HCIFZ KL. L.G L7M P5Z P62 PCBAR PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS DOA |
| DOI | 10.5194/amt-14-5637-2021 |
| DatabaseName | Aqualine Meteorological & Geoastrophysical Abstracts Oceanic Abstracts Water Resources Abstracts Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest One Sustainability ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Continental Europe Database ProQuest Technology Collection Natural Science Collection Earth, Atmospheric & Aquatic Science Collection Environmental Sciences and Pollution Management ProQuest One ProQuest Central Korea ASFA: Aquatic Sciences and Fisheries Abstracts Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources SciTech Premium Collection Meteorological & Geoastrophysical Abstracts - Academic Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Earth, Atmospheric & Aquatic Science Database ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China DOAJ Directory of Open Access Journals |
| DatabaseTitle | Publicly Available Content Database Aquatic Science & Fisheries Abstracts (ASFA) Professional Technology Collection Technology Research Database ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China Water Resources Abstracts Environmental Sciences and Pollution Management Earth, Atmospheric & Aquatic Science Collection ProQuest Central ProQuest One Applied & Life Sciences Aerospace Database ProQuest One Sustainability Meteorological & Geoastrophysical Abstracts Oceanic Abstracts Natural Science Collection ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Collection ProQuest One Academic Eastern Edition Earth, Atmospheric & Aquatic Science Database ProQuest Technology Collection Continental Europe Database ProQuest SciTech Collection Aqualine Advanced Technologies & Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ProQuest One Academic UKI Edition ASFA: Aquatic Sciences and Fisheries Abstracts ProQuest One Academic Meteorological & Geoastrophysical Abstracts - Academic ProQuest One Academic (New) |
| DatabaseTitleList | Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Meteorology & Climatology |
| EISSN | 1867-8548 |
| EndPage | 5655 |
| ExternalDocumentID | oai_doaj_org_article_6fbd647cf5114557a082ddc7ac2aca27 |
| GroupedDBID | 23N 5VS 7QH 7TG 7TN 7UA 8FD 8FE 8FG 8FH 8R4 8R5 AAFWJ ABDBF ABUWG ACGFO ACUHS ADBBV AEGXH AENEX AEUYN AFKRA AFPKN AFRAH AHGZY AIAGR ALMA_UNASSIGNED_HOLDINGS ARAPS AZQEC BCNDV BENPR BFMQW BGLVJ BHPHI BKSAR BPHCQ C1K CCPQU D1K DWQXO E3Z ESX F1W GROUPED_DOAJ H13 H8D H96 HCIFZ IAO IEA ISR ITC K6- KL. KQ8 L.G L7M LK5 M7R OK1 P2P P62 PCBAR PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PROAC Q2X RKB RNS TR2 TUS |
| ID | FETCH-LOGICAL-d249t-d9a0e9a931f1340d84918d45e43f77fe0968f7e474797bcdae332de33a449a3a3 |
| IEDL.DBID | BENPR |
| ISICitedReferencesCount | 32 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000687055700002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1867-1381 |
| IngestDate | Fri Oct 03 12:33:53 EDT 2025 Sun Jul 13 05:17:29 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-d249t-d9a0e9a931f1340d84918d45e43f77fe0968f7e474797bcdae332de33a449a3a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://www.proquest.com/docview/2562220892?pq-origsite=%requestingapplication% |
| PQID | 2562220892 |
| PQPubID | 105742 |
| PageCount | 19 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_6fbd647cf5114557a082ddc7ac2aca27 proquest_journals_2562220892 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-08-18 |
| PublicationDateYYYYMMDD | 2021-08-18 |
| PublicationDate_xml | – month: 08 year: 2021 text: 2021-08-18 day: 18 |
| PublicationDecade | 2020 |
| PublicationPlace | Katlenburg-Lindau |
| PublicationPlace_xml | – name: Katlenburg-Lindau |
| PublicationTitle | Atmospheric measurement techniques |
| PublicationYear | 2021 |
| Publisher | Copernicus GmbH Copernicus Publications |
| Publisher_xml | – name: Copernicus GmbH – name: Copernicus Publications |
| SSID | ssj0064172 |
| Score | 2.4590547 |
| Snippet | Low-cost air pollution sensors often fail to attain sufficient performance compared with state-of-the-art measurement stations, and they typically require... |
| SourceID | doaj proquest |
| SourceType | Open Website Aggregation Database |
| StartPage | 5637 |
| SubjectTerms | Air pollution Air pollution measurements Algorithms Calibration Costs Extrapolation Gaussian process Humidity Laboratories Learning algorithms Limiting factors Low cost Machine learning Measurement Methods Nitrogen dioxide Particulate emissions Particulate matter Performance evaluation Pollutants Pollution levels Regression Regression analysis Relocation Sensors Stations Statistical analysis Suspended particulate matter Training Urban areas |
| SummonAdditionalLinks | – databaseName: Copernicus Publications dbid: RKB link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQ1QMXoAXEQovmgLhZjR9Z271B1YpDd6kQoN6iie2UlbabKgmteuh_79gJUiUOHOglUt6jmbH9jcf-hrEPooi-xFrzEr3nOgbPayWRl7YJpSpcbXLluZ-nZrm05-fu7EGpr7QmbKQHHhV3MG_qMNfGN4QMdFkapDErBG_QS_Qo0z5ycsPUJL-lGm5jHzzXIpdtSmxtiWVPjAlKQiv6AC8HLki2uTLkIokjNJP1_9UX5wHm5Pl_iPaCPZtQJXwaX9lhT-Jml80WBIjbLs-bw0c4Wq8Ineazl-xukRdRRpiqRlwA2SpFzslO0Dawbm-4b_sBll8l4CbA2UIU0FPQ23b9IWzaDU8AFTvA9UXbrYZfl31-LmceYNx8CfStlJ2GIcPj2I2k4Lev2I-T4-9HX_hUiYEHCs8GHhwW0aFTohFKF8FqJ2zQZdSqMaaJFAfZxkRNsYkztQ8YlZKBDqi1Q4XqNdsiweIbBtJabaWnbq02dK8mhB-iD9rLFLnVesY-J0VXVyPZRpXor_MF0nw1ab76l-ZnbO-PMaupTfYVgTsCQ4V18u1j_OMde5rcJ80vC7vHtobud9xn2_56WPXd--yO93875M0 priority: 102 providerName: Copernicus Gesellschaft – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELbQigOXivIQW7ZoDoib1fiRtd1bu6LiwC49AOotmthOu9J2UyWBigP_nbGTSkg9cOESKQ8l1sxk_H1-fMPYe1FEX2KteYnecx2D57WSyEvbhFIVrja58tz3z2azsVdX7vKvUl9pTdgoDzwa7mTZ1GGpjW8IGeiyNEh9VgjeoJfoUeZ95IVxD2RqzMFLLXLZpqTWllT2xDhBSWhFn-DtwAW1bakMhUjSCM1i_Y9yce5gLp6zgwkZwtnYokP2JO5fsPmaQG3b5bFv-ACr3ZYQZj57yX6v80LICFPlh2sgeyf2m2wNbQO79p77th9g80UC7gNcrkUBPRHXtutPgYg_TyATO8Ddddtth5vbPj-XZw9g3EAJ9K40wwxDhrixG4W9f71i3y4-fl194lM1BR6IYg08OCyiQ6dEI5QugtVO2KDLqFVjTBOJy9jGRE38wpnaB4xKyUAH1NqhQvWazahh8Q0Daa220lNqqg3dqwmlh-iD9jKxr1rP2XkyaXU3CmZUScI6XyDHVpNjq385ds4WDw6ppv-qrwigEaAprJNH_-Mbb9mzFAJpjFjYBZsN3Y94zJ76n8O2797lkPoDlK_SQQ priority: 102 providerName: Directory of Open Access Journals |
| Title | Machine learning calibration of low-cost NO2 and PM10 sensors: non-linear algorithms and their impact on site transferability |
| URI | https://www.proquest.com/docview/2562220892 https://doaj.org/article/6fbd647cf5114557a082ddc7ac2aca27 |
| Volume | 14 |
| WOSCitedRecordID | wos000687055700002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAGF databaseName: Copernicus Publications customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: RKB dateStart: 20080101 isFulltext: true titleUrlDefault: http://publications.copernicus.org/open-access_journals/open_access_journals_a_z.html providerName: Copernicus Gesellschaft – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: DOA dateStart: 20080101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: P5Z dateStart: 20100501 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Continental Europe Database customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: BFMQW dateStart: 20100501 isFulltext: true titleUrlDefault: https://search.proquest.com/conteurope providerName: ProQuest – providerCode: PRVPQU databaseName: Earth, Atmospheric & Aquatic Science Database customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: PCBAR dateStart: 20100501 isFulltext: true titleUrlDefault: https://search.proquest.com/eaasdb providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: BENPR dateStart: 20100501 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1867-8548 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0064172 issn: 1867-1381 databaseCode: PIMPY dateStart: 20100501 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwELZa6KGX0qdYoMgH1JtF_Mja5oJYBGoFu41QW9FeIsd2tkjLBpIA6qH_vWPHqx4q9cLFku0oGmnG42_G9jcI7dHM29xUguTGWiK8s6TizJBc1S7nma5krDz37VzOZuryUhcp4dala5UrnxgdtWtsyJHvw9YMW1mmNDu8uSWhalQ4XU0lNJ6i9cBUBna-PjmZFRcrXzwWNJZvCqxtgW2PDgeVgFrEvrnuCQUZx1yCqQSu0Eja_49PjhvN6cZjRXyJXiSIiY8Gm3iFnvjlazSaAjpu2phExx_w8eIKoGrsvUG_p_FGpcephMQcg-JCGB2UhpsaL5oHYpuux7PPDJulw8WUZriDCLhpuwO8bJYkoFXTYrOYg0T9z-sufhePIfDwEhPDv4KkuI9Y2bcDQ_ivt-jr6cmX448klWUgDmK1njhtMq-N5rSmXGROCU2VE7kXvJay9hAUqVp6AYGKlpV1xnPOHDRGCG244e_QGgjmNxFmSgnFLPi4SsJcBXDfeeuEZSGMq8QITYJOypuBeaMMXNhxoGnnZVpa5biu3FhIWwN2FHkuDaAa56w0lhlrmByhnZW6yrRAu_Kvrrb-P72NngfrCGlkqnbQWt_e-ffomb3vr7p2N9nbbgzloS3yHzBWfJoW36F3cTb5A4vu5XU |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VLRJcKJ9ioYAPwM1qYjtrBwlVUKi66mbZQ0HlFBzbWSptNyUJVD3wl_obO3YScUDi1gOXSIkjK5o8zbzx2PMAXsaRM4kuBE20MVQ4a2jBmaaJKm3Co7SQQXnuy0zO5-r4OF1swOVwFsZvqxx8YnDUtjJ-jXwHQzOGskilbPfsB_WqUb66OkhodLA4dBfnmLI1b6cf8P--Ymz_49HeAe1VBajFVKOlNtWRS3XK4zLmIrJKpLGyInGCl1KWDjm9KqUTyLNTWRirHefM4kULkWquOc57AzYFgj0aweZimi2-Dr5_IuIgF-W7xPnufnFXGEWWJHb0aUtjtMmES4Sm700aRAL-igEhsO1v_W8muQt3egpN3nWYvwcbbn0fxhmy_6oORQLymuytTpCKh7sH8DsLO0Yd6SUylgSB6ZcJPChJVZJVdU5N1bRk_okRvbZkkcURaTDDr-rmDVlXa-rZuK6JXi3RAu330ya8F8ospDtpSnAubxnShlzA1V0H9IuH8PlarPEIRvhh7jEQppRQzKAPLySOFZjOWGesMMynqYUYw3uPgfys6yyS-17f4UFVL_PedeSTsrATIU2J3FgkidTI2qw1UhumjWZyDNsDPPLeATX5H2w8-ffwC7h1cJTN8tl0fvgUbntk-iXzWG3DqK1_umdw0_xqT5r6eY91At-uG0tXT4s9bA |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VLUJc-EZsKeADcLM2sZ21g4QQ_VhRtRtWCFBvqWM7S6Xtpk0CVQ_8MX4dYycRByRuPXCJlDiKosnLzHseewbgZRw5k-hC0EQbQ4WzhhacaZqo0iY8SgsZOs99PZJZpo6P08UG_Br2wvhllYNPDI7aVsbPkU8wNGMoi1TKJmW_LGKxN3t3fkF9BymfaR3aaXQQOXRXlyjfmrcHe_itXzE22_-8-4H2HQaoRdnRUpvqyKU65XEZcxFZJdJYWZE4wUspS4f8XpXSCeTcqSyM1Y5zZvGghUg11xyfewM2JUfRM4LNnf1s8WmIA1MRh9ZRvmKcr_QXd0lSZExios9aGqN9plwiTH2d0tAw4K94EILc7O7_bJ57cKen1uR99y_chw23fgDjOaqCqg7JA_Ka7K5OkaKHs4fwcx5WkjrSt85YEgSsnz7wYCVVSVbVJTVV05LsIyN6bcliHkekQeVf1c0bsq7W1LN0XRO9WqIF2m9nTbgvpF9ItwOV4LO8ZUgbNIKru8roV4_gy7VY4zGM8MXcEyBMKaGYQd9eSBwrUOZYZ6wwzMvXQoxhx-MhP-8qjuS-Bni4UNXLvHcp-bQs7FRIUyJnFkkiNbI5a43UhmmjmRzD9gCVvHdMTf4HJ1v_Hn4BtxBA-dFBdvgUbnuQ-pn0WG3DqK2_u2dw0_xoT5v6eQ97AifXDaXfzEBGBg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Machine+learning+calibration+of+low-cost+NO2+and+PM10+sensors%3A+non-linear+algorithms+and+their+impact+on+site+transferability&rft.jtitle=Atmospheric+measurement+techniques&rft.au=Nowack%2C+Peer&rft.au=Konstantinovskiy%2C+Lev&rft.au=Gardiner%2C+Hannah&rft.au=Cant%2C+John&rft.date=2021-08-18&rft.pub=Copernicus+GmbH&rft.issn=1867-1381&rft.eissn=1867-8548&rft.volume=14&rft.issue=8&rft.spage=5637&rft.epage=5655&rft_id=info:doi/10.5194%2Famt-14-5637-2021&rft.externalDBID=HAS_PDF_LINK |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1867-1381&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1867-1381&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1867-1381&client=summon |